Eventual-Inc/Daft
High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale
Built on Apache Arrow with a vectorized execution engine and query optimizer, it enables efficient processing of mixed data types in a single dataframe. Includes native LLM inference, embedding generation, and classification operations integrated with OpenAI, Hugging Face, and custom models. Scales seamlessly from local Python execution to Ray or Kubernetes clusters while maintaining intelligent memory management for out-of-core workloads.
5,301 stars. Used by 1 other package. Actively maintained with 163 commits in the last 30 days. Available on PyPI.
Stars
5,301
Forks
414
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
163
Dependencies
5
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mlops/Eventual-Inc/Daft"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.